English

Harnessing data-driven methods for precise model independent event shape estimation in relativistic heavy-ion collisions

High Energy Physics - Phenomenology 2025-11-25 v3

Abstract

This study demonstrates the application of supervised machine learning (ML) techniques to distinguish between isotropic and jet-like event topologies in heavy-ion collisions via the spherocity observable. State-of-the-art ML algorithms, optimized through systematic hyperparameter tuning, are employed to predict both traditional transverse spherocity S0S_{0} and unweighted transverse spherocity S0pT=1S_{0}^{p_{\rm T}=1} directly from raw event data. Moreover, the results from this study demonstrated that our approach remains largely model-independent, underscoring its potential applicability in future experimental heavy-ion physics analyses.

Keywords

Cite

@article{arxiv.2508.13349,
  title  = {Harnessing data-driven methods for precise model independent event shape estimation in relativistic heavy-ion collisions},
  author = {Dipankar Basak and H. Hushnud and Kalyan Dey},
  journal= {arXiv preprint arXiv:2508.13349},
  year   = {2025}
}

Comments

10 pages, 7 figures

R2 v1 2026-07-01T04:55:39.607Z